NETSCOUT has showcased the potential of AI-driven automation in telecom operations through its participation in TM Forum’s NeuroNOC: The Self-Healing Network Brain Catalyst project. Presented at DTW Ignite 2025 in Copenhagen, the project brought together a wide coalition of telecom and technology players focused on enabling real-time, self-healing capabilities in next-generation networks.
The NeuroNOC Catalyst included contributions from NETSCOUT, Amazon Web Services (AWS), Accenture, Symphonica, and Sand Technologies. It was championed by communication service providers including BT Group, Telecom Argentina, Omantel, Turknet, Axian Telecom, and Safaricom. The project aimed to demonstrate how high-quality telemetry data, combined with closed-loop automation and AI agents, could drastically improve network operations. Using TM Forum’s Open APIs and Open Digital Architecture, the project unified diverse data streams—such as alarms, logs, performance metrics, and topology—into a centralized platform for AI analysis.
NETSCOUT deployed its Omnis AI Sensor and Omnis AI Streamer to deliver deep packet inspection (DPI)-based visibility and real-time analytics across simulated 5G Standalone Radio Access Network (SA RAN) and Packet Core scenarios. When a service-impacting issue was introduced, the AI system—leveraging a curated large language model—identified subscriber registration failures, pinpointed the root cause, and executed remediation with minimal human input. The outcomes were significant: up to 80% reduction in manual troubleshooting, 50% reduction in operational costs, and an estimated 80% drop in AI model tokenization demands on AWS Bedrock, signaling substantial cost savings.
“Accurate, real-time curated data is the foundation of intelligent network operations,” said Richard Fulwiler, Senior Director of Product Management at NETSCOUT. “While fully autonomous networks are still in their early stages, this project shows the powerful potential of AI agents – armed with the right data in real-time – to support faster and more accurate resolution of network issues.”
